Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards Effective Deep Neural Network Approach for Multi-Trial P300-based Character Recognition in Brain-Computer Interfaces

Praveen Kumar Shukla, Hubert Cecotti, Yogesh Kumar Meena

TL;DR

This work proposes a weighted ensemble spatiosequential convolutional neural network (THE AUTHORS-SPSQ-CNN) to improve classification accuracy and SNR by mitigating signal variability for character identification within oddball paradigms.

Abstract

Brain-computer interfaces (BCIs) enable direct interaction between users and computers by decoding brain signals. This study addresses the challenges of detecting P300 event-related potentials in electroencephalograms (EEGs) and integrating these P300 responses for character spelling, particularly within oddball paradigms characterized by uneven P300 distribution, low target probability, and poor signal-to-noise ratio (SNR). This work proposes a weighted ensemble spatio-sequential convolutional neural network (WE-SPSQ-CNN) to improve classification accuracy and SNR by mitigating signal variability for character identification. We evaluated the proposed WE-SPSQ-CNN on dataset II from the BCI Competition III, achieving P300 classification accuracies of 69.7\% for subject A and 79.9\% for subject B across fifteen epochs. For character recognition, the model achieved average accuracies of 76.5\%, 87.5\%, and 94.5\% with five, ten, and fifteen repetitions, respectively. Our proposed model outperformed state-of-the-art models in the five-repetition and delivered comparable performance in the ten and fifteen repetitions.

Towards Effective Deep Neural Network Approach for Multi-Trial P300-based Character Recognition in Brain-Computer Interfaces

TL;DR

This work proposes a weighted ensemble spatiosequential convolutional neural network (THE AUTHORS-SPSQ-CNN) to improve classification accuracy and SNR by mitigating signal variability for character identification within oddball paradigms.

Abstract

Brain-computer interfaces (BCIs) enable direct interaction between users and computers by decoding brain signals. This study addresses the challenges of detecting P300 event-related potentials in electroencephalograms (EEGs) and integrating these P300 responses for character spelling, particularly within oddball paradigms characterized by uneven P300 distribution, low target probability, and poor signal-to-noise ratio (SNR). This work proposes a weighted ensemble spatio-sequential convolutional neural network (WE-SPSQ-CNN) to improve classification accuracy and SNR by mitigating signal variability for character identification. We evaluated the proposed WE-SPSQ-CNN on dataset II from the BCI Competition III, achieving P300 classification accuracies of 69.7\% for subject A and 79.9\% for subject B across fifteen epochs. For character recognition, the model achieved average accuracies of 76.5\%, 87.5\%, and 94.5\% with five, ten, and fifteen repetitions, respectively. Our proposed model outperformed state-of-the-art models in the five-repetition and delivered comparable performance in the ten and fifteen repetitions.

Paper Structure

This paper contains 14 sections, 6 equations, 4 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Methods
  3. Spatio-sequential CNN
  4. Weighted ensemble of SPSQ-CNNs
  5. P300 speller
  6. Character classification
  7. Signal preprocessing
  8. Simulations
  9. Results
  10. P300 speller
  11. Character classification estimation
  12. Character classification rate
  13. Ablation study
  14. Discussion and Conclusion

Figures (4)

  • Figure 1: The architecture of proposed spatio-sequential CNN model for P300 and non-300 classification.
  • Figure 2: The schematic block diagram outlines our proposed framework for character identification in RC-based P300 Speller. It employs a band-pass filter and signal averaging for data prepossessing, with P300 classification and character recognition achieved through WE-SPSQ CNN classification.
  • Figure 3: Participants are presented with the target word 'SEND' in the P300-based Row-Column BCI Paradigm farwell1988talking
  • Figure 4: ROC for both subjects A and B.